© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 24313
    Prev
    Next
    INDEX
    Explanations

    technical error messages indicative of a problem or failure

    oai_token-act-pair · gpt-3.5-turbo

    messages related to account or technical issues, particularly those requiring user action

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     caric
    -0.83
    icipated
    -0.81
     particip
    -0.79
     cultivated
    -0.79
    folios
    -0.76
    quartered
    -0.75
     societies
    -0.74
     embraced
    -0.74
     embraces
    -0.73
     charismatic
    -0.73
    POSITIVE LOGITS
     workaround
    1.42
    Solution
    1.22
     disabling
    1.20
     outage
    1.16
     Symptoms
    1.14
     Fixes
    1.13
     FIX
    1.13
     uninstall
    1.12
    Fix
    1.11
    Sym
    1.08
    Activations Density 1.017%

    No Known Activations